American Journal of Engineering Research (AJER) 2017 American Journal of Engineering Research (AJER) e-ISSN: 2320-0847 p-ISSN : 2320-0936 Volume-6, Issue-1, pp-226-239 www.ajer.org Research Paper Open Access www.ajer.org Page 226 A Comprehensive Survey on Extractive Text Summarization Techniques Aysa Siddika Asa 1 , Sumya Akter 2 , Md. Palash Uddin 3 , Md. Delowar Hossain 4 , Shikhor Kumer Roy 5 , Masud Ibn Afjal 6 3,4,6 (Department of Computer Science and Engineering, Hajee Mohammad Danesh Science and Technology University (HSTU), Dinajpur-5200, Bangladesh) 1,2,5 (B.Sc. in Computer Science and Engineering, Hajee Mohammad Danesh Science and Technology University (HSTU), Dinajpur-5200, Bangladesh) ABSTRACT: Automated data collection tools and matured database technology lead to tremendous amounts of data stored in database, data warehouses and other data repositories. With the increasing amount of online information, it becomes extremely difficult to find relevant information to users. Information retrieval system usually returns a large amount of documents listed in the order of estimated relevance. It is not possible for users to read each document in order to find the useful one. Automatic text summarization system, one of the special data mining applications, helps in this task by providing a quick summary of the information contained in the document(s). Some efficient work has been done for text summarization on various languages. But among them there are a few works on Bengali language. It has thus motivated us to do develop or modify a new or existing summarization technique for Bengali document(s) and to provide us an opportunity to make some contribution in natural language processing. To do the same, we have surveyed and compared some techniques on extractive text summarization on various languages in this paper. The summarizations have done for single or multiple documents in different languages. Finally, a comparative nomenclature on the discussed single or multi-document summarization techniques has been conducted. Keywords: big data, data mining, extractive summarization, text mining, text summarization I. INTRODUCTION Nowadays, there exist a lot of amount of data and this rapid growth of data is required to process, store, and manage. Sometimes, it is difficult to find the exact information from large amount of stored data or big data. Today, in the era of big data, textual data is rapidly growing and is available in many different languages. Big data has the potential to be mined for information and data mining is essential to find out the proper information what we need [1]. Search engines such as Google, AltaVista, Yahoo, etc., have been developed to retrieve specific information from this huge amount of data. But most of the time, the outcome of search engine is unable to provide expected result as the quantity of information is increasing enormously day by day and also the findings are abundant [2]. Knowledge discovery (e.g. text mining) from large volumes of data has seen sustained research in recent years. As a field of data mining, text summarization is one of the most popular research areas to extract main theme from large volume of data. This process reduces the problem of information overload because only a summary needs to be read instead of reading the entire document. This can comprehensively help the user to make out ideal documents within a short time by providing scraps of information [3]. 1.1 Data Mining Data mining is a very growing application field for the researchers. It is the process of extracting some meaningful information from chunks of meaningless data whereas text mining is about looking for pattern in text. The information overload problem leads to wastage of time for browsing all the retrieval information and there may have a chance to miss out relevant information [4]. The roots of data mining are traced back along with three family lines: classical statistics, artificial intelligence, and machine learning [5], [6]. Typical data mining tasks include document classification, document clustering, building ontology, sentiment analysis, document summarization, information extraction etc.Data mining utilizes descriptive and predictive approaches in order to discover hidden information. Data mining satisfies its main goal by identifying valid, potentially useful, and easily understandable correlations and patterns present in existing data. This goal of data mining can be satisfied by modeling it as either predictive or descriptive nature [7]. Predictive approaches include classification, regression or prediction, time series analysis etc. whereas descriptive approaches include clustering, summarization, association rules, sequence discovery etc.
14
Embed
A Comprehensive Survey on Extractive Text Summarization …ajer.org/papers/v6(01)/ZH0601226239.pdf · 2017-02-23 · For multi-document summarization, the process needs to extend.
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
American Journal of Engineering Research (AJER) 2017
American Journal of Engineering Research (AJER)
e-ISSN: 2320-0847 p-ISSN : 2320-0936
Volume-6, Issue-1, pp-226-239
www.ajer.org
Research Paper Open Access
w w w . a j e r . o r g
Page 226
A Comprehensive Survey on Extractive Text Summarization
Techniques
Aysa Siddika Asa1, Sumya Akter
2, Md. Palash Uddin
3, Md. Delowar Hossain
4,
Shikhor Kumer Roy5, Masud Ibn Afjal
6
3,4,6(Department of Computer Science and Engineering, Hajee Mohammad Danesh Science and Technology
University (HSTU), Dinajpur-5200, Bangladesh) 1,2,5
(B.Sc. in Computer Science and Engineering, Hajee Mohammad Danesh Science and Technology University
(HSTU), Dinajpur-5200, Bangladesh)
ABSTRACT: Automated data collection tools and matured database technology lead to tremendous amounts
of data stored in database, data warehouses and other data repositories. With the increasing amount of online
information, it becomes extremely difficult to find relevant information to users. Information retrieval system
usually returns a large amount of documents listed in the order of estimated relevance. It is not possible for
users to read each document in order to find the useful one. Automatic text summarization system, one of the
special data mining applications, helps in this task by providing a quick summary of the information contained
in the document(s). Some efficient work has been done for text summarization on various languages. But among
them there are a few works on Bengali language. It has thus motivated us to do develop or modify a new or
existing summarization technique for Bengali document(s) and to provide us an opportunity to make some
contribution in natural language processing. To do the same, we have surveyed and compared some techniques
on extractive text summarization on various languages in this paper. The summarizations have done for single
or multiple documents in different languages. Finally, a comparative nomenclature on the discussed single or
multi-document summarization techniques has been conducted.
Keywords: big data, data mining, extractive summarization, text mining, text summarization
I. INTRODUCTION Nowadays, there exist a lot of amount of data and this rapid growth of data is required to process, store, and
manage. Sometimes, it is difficult to find the exact information from large amount of stored data or big data. Today, in
the era of big data, textual data is rapidly growing and is available in many different languages. Big data has the
potential to be mined for information and data mining is essential to find out the proper information what we need [1].
Search engines such as Google, AltaVista, Yahoo, etc., have been developed to retrieve specific information from this
huge amount of data. But most of the time, the outcome of search engine is unable to provide expected result
as the quantity of information is increasing enormously day by day and also the findings are abundant [2].
Knowledge discovery (e.g. text mining) from large volumes of data has seen sustained research in recent years. As a
field of data mining, text summarization is one of the most popular research areas to extract main theme from large
volume of data. This process reduces the problem of information overload because only a summary needs to be read
instead of reading the entire document. This can comprehensively help the user to make out ideal documents within a
short time by providing scraps of information [3].
1.1 Data Mining Data mining is a very growing application field for the researchers. It is the process of extracting some
meaningful information from chunks of meaningless data whereas text mining is about looking for pattern in text. The
information overload problem leads to wastage of time for browsing all the retrieval information and there may have a
chance to miss out relevant information [4]. The roots of data mining are traced back along with three family lines:
classical statistics, artificial intelligence, and machine learning [5], [6]. Typical data mining tasks include document
classification, document clustering, building ontology, sentiment analysis, document summarization, information
extraction etc.Data mining utilizes descriptive and predictive approaches in order to discover hidden information. Data
mining satisfies its main goal by identifying valid, potentially useful, and easily understandable correlations
and patterns present in existing data. This goal of data mining can be satisfied by modeling it as either predictive or
descriptive nature [7]. Predictive approaches include classification, regression or prediction, time series analysis etc.
whereas descriptive approaches include clustering, summarization, association rules, sequence discovery etc.
American Journal of Engineering Research (AJER) 2017
w w w . a j e r . o r g
Page 227
1.2 Data Mining Algorithms and Applications Data mining uses different techniques such as statistical, mathematical, artificial intelligence and machine
learning as the computing techniques [7]. The techniques and algorithms for data mining are Naive Bayes decision
theory, support vector machine (SVM), decision tree etc. for classification or logistic regression; multiple regression,
SVM etc. for regression; minimum description length for attribute importance;one-class SVM for anomaly detection;
Figure2: A Multi document text Summarization using sentence clustering
d) Multi-document summary generation:
Sentences appearing in single document summaries are clustered, Top scoring sentences are extracted from
each cluster and the sentences are arranged according to their position in the original document to generate the final
multi-document summary as shown in Fig. 2.
Sentence clustering: It usessyntactic and semantic similarity.
Syntactic similarity: For example,
S1= the cat runs faster than a rat, S2=the rat runs faster than a cat, Index no. for S1={1,2,3,4,5,6,7}, Index no for
S2={1,2,3,4,5,6,7}, Original order Vector,V0={1,2,3,4,5,6,7}, Original order Vector, Vr={ } So, the
semantic similarity will be as follows:
∑
∑ ∑
∑ ∑
∑
∑
Here,K=number of words in S1and maximum value of syntactic similarity is 1 when the original and relative word is
same.
Semantic similarity:Semantic similarity between words i.e.,creating a graph.
o Shortest path lengthIf the words are similar, then the shortest path length between them is 0. If the length is less,
then words are more similar and if the length is more, than words are less similar.
o Depth of sub summer
Semantic similarity between words:
Here, d= Depth is the subsume,l=shortest path length and f=transfer function
If words are exactly similar, then similarity=1; (l=0)
If words are dissimilar, then similarity=0; (no common parent)
If both h and l are non-zero, then the similarity between word w1&w2 is defined as follows:
Here, α, β= smoothing factors
Information content:
Probability of words,
Here, n=Frequency of the word in the corpus and w=Total no. of words in the corpus.
Now, the semantic similarity is: ∑
∑ ∑ (37)
Overall similarity between two sentences is
( ( ))
( ( ))
Here,δ=Smoothing factor
Thus for multi-document summary, the sentences are clustered using sentence similarity from each cluster and then
single sentence is extracted.
2.8 Paper VIII A. R. Deshpandeet. al. [23] presented a text summarizer using clustering technique as shown in Fig. 3.
American Journal of Engineering Research (AJER) 2017
w w w . a j e r . o r g
Page 235
Document
collection query
Strengthen query
prepocessing
Calculate sentence score by using features
Documents are clustered using cosine similarity
C1 C2 ……. Cn
Calculate the score of each sentence cluster & sort sentence clusters in
Pick the best scored sentences from each sentence cluster & add it to the summary
Figure3. Document & Sentence clustering approach to summarization
It is the clustering based approach that groups first the similar documents into clusters and then sentences
from every document cluster are clustered into sentence clusters. And best scoring sentences from sentence clusters
are selected into the final summary. For finding similarity, cosine similarity is used. It merged sentence and query.
Then each word from the merged sentence is taken and checked whether that word appears in sentence and query
both. If yes, then the weight ( of the word from document is used and placed that value in vector of sentence
for the location in vector, and term frequency of the term is placed in vector of query.
2.9 Paper IX and proposed [24] an extraction based summarization technique using k-means
clustering algorithm which is an unsupervised learning technique. Thescore for each sentenceis computed and
centroid based clustering is applied on the sentences and extracting important sentences as part of summary.In this
paper, tokenization method occurs as follows:
All contiguous strings of alphabetic characters are part of one token; likewise with numbers
Tokens are separated by whitespace characters, such as a space or line break, or by punctuation characters
Punctuation and whitespace may or may not be included in the resulting list of tokens
For computing the score of sentence, first the TF*IDF of each individual words in the sentence is calculated.
Then,K-means clustering algorithm is applied. The main idea is to define k centroids, one for each cluster.
These centroids are chosen to place them as much as possible far away from each other. This approach gives a precise
summary because the densest cluster which is returned by the K-means clustering algorithm that consists of the
sentences with highest scores in the entire document. These sentence scores are computed by summing up the scores of individual terms in the sentence and normalizing it by using the length of the sentence. .
2.10 Paper X M. A. Uddinet. al. [25] presented a multi-document text summarization for Bengali text, where
termfrequency (TF) based technology is used for extracting the most significant contents from a set of Bengali
documents. Pre-processing includes tokenization, elimination or removal of punctuation characters, numeric digits,
stop word etc.
The total term frequency (TTF) is measured bycounting the total numbers of appearances of a word in all the
documents.
∑
Here j= 1, 2, 3 ….n number of documents.
I. Sentence Scoring (SC)
Score of a sentence is determined by summing up TTF of each word in that sentence as follows:
∑ if all the sentences have the same length
Sentence score of a long sentence is greater than a short sentence. And also smaller sentence is more meaningful than
the larger one. So, SC is found by ordering in decreasing order and the total words found in the document.
Or, ∑
Here,
, of words in each sentence.T=total word,
and L=word position.
II. Primary Summarization
SCs are sorted in decreasing order, k sentences are chosen as primary summarized content.To choose two
sentences having identical meaning, this method would prefer one which is more descriptive and represents the
American Journal of Engineering Research (AJER) 2017
w w w . a j e r . o r g
Page 236
document better than the other one.Let consider, two sentences as vector, given two vectors of attributes , so we
get,
i. Cosine similarity measure: = Cos Θ
∑
∑
∑
Here, =TTF of words in two sentences , indicates that
Dissimilarity<Independence<Similarity.
ii. ∑
∑
(40)
Here, = Average sentence similarity, = Maximum similarity or threshold value ∩
, then
Here ( )
, ( ) Let consider, ,
, as shown in table 2.
Table 2: A simple probability calculation for generating sentence relevancy S1 S2 S3
S1 1 0.5 0.5 0.625
S2 0.5 1 0.5 0.625
S3 0.5 0.5 1 0.625
Every sentence is considered as a node and P ( is the weight of the edge connecting to the node
As a result, we get an undirected graph. The sentence having largest value is chosen to be the first
sentence. For finding the best relevancy of sentences, the A* search algorithm is applied. Then it will find the final
summary.
2.11 Paper XI Another work proposed by M. I. A. Efatet.al. [26] by sentence scoring andranking for Bengali language.
Pre-processing:
It includes tokenization, stop words removal (but, or, and am, is, are, a, an, the etc.) and stemming.
Sentence Scoring & Summarization:
i.Frequency: ∑
Here, = Sentence Total Frequency, WF=Word Frequency and n=number of words in a sentence.
ii. Positional Value:
Here, k=the actual positional value of a sentence in the document.
iii. Cue words consist of “therefore”,“hence”, “lastly”, “finally”, “meanwhile”, on the other hand etc. and skeleton
word of the documentconsists of the words in tittle and headers.
Sentence scoring is done as follows:
Here,α=0.1, β=0, γ=0.7(Cue words co-factor) and λ=0.4(Skeleton co-factor of the document)
iv. Summary Making: After ranking the sentences based on , X number of top ranked sentences are selected for
producing the summary. Comparison between the human summarizer and the machine summarizer can be measured
by three equations. For each document, we let kh be the length of the human summary, km the length of the machine
generated summary and the r the number of sentences they share in common. The method defined precision (P),
Recall (R) as metrics, then
and
.
2.12 Paper XII
H. Dave and S. Jaswal [28] presented a multi-document summarization system using hybrid summarization
techniques. There are two main blocks in proposed model, an extractive summary and an abstractive summary.
Steps for generating extractive summary are as follows-
Linguistic Analysis:It extracts sentences from the input documents, and then performs tokenization [11]. Redundancy
Detection:In multiple documents there are chances of repetition of sentences. Hence redundancy detection is
important to reduce the unwanted and repetitive sentences or words. This process is carried out using stop word
removal and stemming.Sentence Representation:Sentence representation is the process of calculating the frequency of
relevant sentences weight.
Term Frequency: Each entry of a sentence vector denotes the term weight which is explained by the equation:
∑ (42)
American Journal of Engineering Research (AJER) 2017
w w w . a j e r . o r g
Page 237
Where is the number of occurrences of term in sentence and ∑ is the sum of number of occurrences of
all the terms in sentence, .The last process is the generation of summary. Sentence representation is used to find the
score (weight) of word from each sentences. This score is assigned to each sentence and generates the highest rank by:
(43)
Steps for generating abstractive summary are as follows-
Word Graph Generation:Word graph generation is phase of finding out important nodes from extractive
summary. Here, a set of heuristic rules are applied such as hypernymy, holonymy, and entailment. Domain Ontology:
According to Tom Gruber ontologyis a specification of a conceptualization [29]. It provides a vocabulary and set of
Synset. This synset consist of Synonym, Antonym etc. Ontology represents the domain which talks about the same
topic having same knowledge. Here the domain ontology is defined by domain experts. Next meaningful terms are
produced by preprocessing and classifier classifies those terms.
WordNet: WordNet is lexical database of English. It is used to define word meaning and models. It consists
of a set of synonyms called as synsets, and is also used as combination of dictionary and thesaurus. The Synsets
provide different semantic relationships such as synonymy (similar) and antonym (opposite), hypernym (super
concept)/hyponymy (sub concept), meronymy (part-of) and holonymy (has-a). Hyponym shares a type-of relationship
with its hypernym. Meronymy is defined as a word that denotes a constituent part or a member of something.
2.13 Paper XIII F. E. Gunawan, A. V. Juandi and B. Soewito [30] presented an automatic text summarization using text
features and singular value decomposition for popular articles in Indonesia language. The scoring procedure is
described as follows:
TF-IDFWeighting: The notation denotes the frequency of the i word appears in the document;
meanwhile, the notation denotes the inverse of the number of sentences that has the i word.
Singular Value Decomposition (SVD): The above TF-IDF process results in the terms-by-sentences matrix, A € .
The number of rows m denotes the number of words and n is the number of sentences in the article. The entity in
the matrix denotes the frequency of the i word in the j sentence. The matrix A is usually a sparse matrix. Subsequently,
the matrix is decomposed into three matrices by the singular value decomposition: A= , where U is the matrix of
the left singular vectors, S is the matrix of the singular values, and V is the matrix of the right singular vectors. The
SVD text summarization procedure can be performed with the steps described in algorithm as follows:
Step i: Decompose the document into sentences
Step ii: k <- 1
Step iii: Establish the terms-by-sentences matrix A
Step iv: A =
Step v: while (required), do
Step vi: Take the kth singular vector in V
Step vii: Put the sentence associated with the singular vector into the summary
Step viii: k <- k + 1
Step viii: End
Word Stemming:This process intends to remove all suffixes from words and produces their roots.
Performance Evaluation: The performance of the current implementation is measured by
=
Recall=
, F=2
III. RESULT AND COMPARATIVE DISCUSSION The comparative result of the reviewed papers is illustrated in the following table.
Table 3: Comparative study of proposed technique with existing methods
Paper no. Language Document type Major operations
Paper I[17] English Single(Graph
based)
Subtopic detection(KNN), word scoring (TF*IDF),
ranking sentences(calculating Hub & Authority),
ordering subtopic(Markov model)
Paper
II[18]
English Single Preprocessing,measure relevancy(PMI),
Word significance estimation
Paper III
[19]
Chinese Single Fuzzy similarity matrix(TF*IDF), maximum spanning
Indonesia Multiple Sentence segmentation, tokenization, stop word
removal, stemming,
TF-IDF weighting, singular value decomposition
IV. CONCLUSION In this paper, the state-of-the-art of extractive text summarization techniques for various languages has been
described. We can notice that good work has been done for various foreign languages like English, Chinese etc. But
summarization system for Bengali languages is still in lack. Hence, it is challenging to propose a summarization
technique using different types of features. In future, we are aiming to use more features for extracting Bengali
sentences. Also, we will try to compare different machine learning techniques for summarization and to achieve better
accurate results. Also, we will try to test the techniques rigorously on large dataset of various domains like news,
autobiography,etc.
REFERENCES [1]. Unnamed, Big Data. [Online]. Available: http://searchcloudcomputing.techtarget.com/definition/big-data-Big-Data [2]. M. Haque, S. Pervin, and Z. Begum, Literature Review of Automatic Multiple Documents Text Summarization, International
Journal of Innovation and Applied Studies, 3(1), 2013, 121-129.
[3]. A. Kogilavani, P. Balasubramani, Clustering and Feature specific sentence extraction based summarization of multi-documents, International Journal of Computer Science & Information Technology (IJCSIT), 2(4), 2010.
[4]. R. M. Chezian,and Ahilandeeswari. G., A Survey on Approaches for Frequent Item Set Mining on Apache Hadoop, International
Journal for Trends in Engineering & Technology, 3(3), 2015. [5]. R. Pradheepa, and K. Pavithra, A Survey on Overview of Data Mining, International Journal of Advanced Research in Computer
and Communication Engineering, 5(8), 2016.
[6]. A. Totewar, Data mining: Concepts and Techniques. [Online]. Available http://www.slideshare.net/akannshat/data-mining-15329899, 2016.
[7]. E. Turban, J. E. Aronson, T. Liang, and R. Sharda, Decision Support and Business Intelligent Systems, Pearson Education, 8th
Edition. [8]. Unnamed, Data mining techniques and algorithm. [Online]. Available http://www.oracle.com/technetwork/database/enterprise-
edition/odm-techniques- Algorithms-097163.html
[9]. Unnamed, Data Mining-Applications & Trends [Online]. Available: ww.tutorialspoint.com/data_mining/dm_applications_trends.htm
[10]. M. Verma, and D. Mehta, A Comparative study of Techniques in Data Mining, International Journal of Emerging Technology and
Advanced Engineering, 4(4). [11]. A. Nenkova and K. McKeown, Automatic Summarization, Foundations and Trends® in Information Retrieval, 5(2–3), 2011, 103–
233.
[12]. A. H. Witten, Text mining. [Online]. Available: http://www.cos.ufrj.br/~jano/LinkedDocuments/_papers/aula13/04-IHW Textmining.pdf
[13]. F. El-Ghannam and T. El-Shishtawy, Multi-Topic Multi-Document Summarizer, International Journal of Computer Science &
Information Technology (IJCSIT), 5(6), 2013. [14]. V. Gupta and G. S, Lehal, A Survey of Text Summarization Extractive Techniques, Journal of Emerging Technologies in Web
Intelligence, 2(3), 2010.
[15]. N. R. Kasture, N. Yargal, N. N. Singh, N. Kulkarni and V. Mathur, A Survey on Methods of Abstractive Text Summarization, International Journal for Research in Emerging Science and Technology,1(6), 2014.
[16]. R. Ferreira, L. de S. Cabral, R. D. Lins , G. P. Silva, F. Freitas , G. D. C. Cavalcanti, R. Lima, S. J. Simskeand L. Favaro, Assessing
sentence scoring techniques for extractive text summarization, ELSIVIER International Journal of Expert systems with Applications, 2013.
[17]. J. Zhang, L. Sun, and Q. Zhou, Cue-based Hub-Authority approach for Multi- document Text Summarization, IEEE International Conference on Natural Language Processing and Knowledge Engineering, China, 2005, 642 – 645.
American Journal of Engineering Research (AJER) 2017
w w w . a j e r . o r g
Page 239
[18]. Y. Ouyang, W. Li, and Q. Lu, An Integrated Multi-document Summarization Approach based on Word Hierarchical
Representation, Proceedings of the ACL-IJCNLP, China, 2009, 113-116.
[19]. X. Li, J. Zhang and M. Xing, Automatic Summarization for Chinese text based on Sub Topic Partition and Sentence Features, IEEE 2nd International Symposium on Intelligence Information Processing and Trusted Computing (IPTC), China, 2011.
[20]. P. Hu, T. He and H. Wang, Multi-View Sentence Ranking for Query-Biased Summarization, IEEE International Conference on
Computational Intelligence and Software Engineering (CISE), China, 2010. [21]. K. Sarkar, Sentence Clustering-based Summarization of Multiple Text Documents, TECHNIA – International Journal of Computing
Science and Communication Technologies, 2(1), 2009.
[22]. T. J. Siddiki and V. K. Gupta, Multi-document Summarization using Sentence Clustering, IEEE Proceedings of 4th International Conference on Intelligent Human Computer Interaction, India, 2012.
[23]. A. R. Deshpande, and Lobo L. M. R. J, Text Summarization using Clustering Technique, International Journal of Engineering Trends and Technology (IJETT), 4(8), 2013.
[24]. A. Agrawal and U. Gupta, Extraction based approach for text summarization using k-means clustering, International Journal of
Scientific and Research Publications, 4(11), 2014. [25]. M. A. Uddin, K. Z. Sultana and M. A. Alom, A Multi-Document Text Summarization for Bengali Text, IEEE International Forum
on Strategic Technology (IFOST), Bangladesh, 2014.
[26]. M. I. A. Efat, M. Ibrahim , H. Kayesh, Automated Bangla Text Summarization by Sentence Scoring and Ranking, IEEE International Conference on Informatics, Electronics & Vision (ICIEV), Bangladesh, 2013.
[27]. L. C. Reddy and Venkatadri. M, A Review on Data mining from Past to the Future, International Journal of Computer Applications,
15(7), 2011. [28]. H. Dave and S. Jaswal, Multiple Text Document Summarization System using Hybrid Summarization Technique,1st International
Conference on Next Generation Computing Technologies (NGCT-2015), India, 2015, 4-5.
[29]. J. A. Kwak and H.-S. Yong, Ontology Matching Based On Hypernym, Hyponym, Holonym, and Meronym Sets in Wordnet, International Journal of Web Semantic Technology (IJWesT),1(2), 2010.
[30]. F. E. Gunawan, A. V. Juandi and B. Soewito, An Automatic Text Summarization using Text Features and Singular Value
Decomposition for Popular Articles in Indonesia Language, IEEE International Seminar on Intelligent Technology and Its Applications, 2015.